Field experiments of nitrogen (N) treatment at five different application rates (0, 75, 150, 225, and 300 kg ha⁻¹) were conducted under pot-seedling mechanical transplanting (PMT) in 2018 and 2019.  Two high-quality and high-yielding hybrids of indica rice, Huiliangyou 898 and Y Liangyou 900, were used in this study.  The N nutrition index (NNI) and accumulated N deficit (N_and), used to assess the N nutrition status in real-time, were calculated for the indica cultivars under PMT with a critical nitrogen concentration (Nc) dilution model based on shoot dry matter (DM) during the whole rice growth stage.  The relationships between NNI and N_and with relative yield (RY) were determined, and accurate N application schemes were developed for hybrids indica rice under PMT.  The results indicated that high application rate of N-fertilizer significantly increased the concentrations of shoot DM and N in aboveground organs during the observed stages in the two cultivars for two years (P<0.05).  The Nc dilution model of hybrid indica cultivars was N_c=4.02DM^−0.42 (R²=0.97) combining the two cultivars under PMT.  Root-mean-square error and normalized root-mean-square error of the curve verification were 0.23 and 10.61%, respectively.  The NNI and N_and ranged from 0.58 to 1.31 and 109 to –55 kg ha⁻¹, respectively, in the two cultivars for all N treatments.  NNI showed a linear relationship with N_and during the entire growth stage (0.53<R²<0.99, P<0.01).  In addition, NNI showed a linear-plateau relationship with RY (0.73<R²<0.92, P<0.01) throughout the observed stages.  These results suggest that the models can accurately diagnose the N-nutrition status and support effective N-fertilizer management in real-time for hybrid indica rice under PMT.

Monitoring pest populations in paddy fields is important to effectively implement integrated pest management.  Light traps are widely used to monitor field pests all over the world.  Most conventional light traps still involve manual identification of target pests from lots of trapped insects, which is time-consuming, labor-intensive and error-prone, especially in pest peak periods.  In this paper, we developed an automatic monitoring system for rice light-trap pests based on machine vision.  This system is composed of an intelligent light trap, a computer or mobile phone client platform and a cloud server.  The light trap firstly traps, kills and disperses insects, then collects images of trapped insects and sends each image to the cloud server.  Five target pests in images are automatically identified and counted by pest identification models loaded in the server.  To avoid light-trap insects piling up, a vibration plate and a moving rotation conveyor belt are adopted to disperse these trapped insects.  There was a close correlation (r=0.92) between our automatic and manual identification methods based on the daily pest number of one-year images from one light trap.  Field experiments demonstrated the effectiveness and accuracy of our automatic light trap monitoring system.